Dilbag Singh1, Manjit Kaur1, Vijay Kumar2, Mohamed Yaseen Jabarulla1, Heung-No Lee1. 1. School of Electrical Engineering and Computer ScienceGwangju Institute of Science and Technology Gwangju 61005 South Korea. 2. Department of Computer Science and EngineeringNIT Hamirpur Hamirpur 177005 India.
Abstract
BACKGROUND: Artificial intelligence techniques are widely used in solving medical problems. Recently, researchers have used various deep learning techniques for the severity classification of Chikungunya disease. But these techniques suffer from overfitting and hyper-parameters tuning problems. METHODS: In this paper, an artificial intelligence-based cyber-physical system (CPS) is proposed for the severity classification of Chikungunya disease. In CPS system, the physical components are integrated with computational algorithms to provide better results. Random forest (RF) is used to design the severity classification model for Chikungunya disease. However, RF suffers from overfitting and poor computational speed problems due to complex architectures and large amounts of connection weights. Therefore, an evolving RF model is proposed using the adaptive crossover-based genetic algorithm (ACGA). RESULTS: ACGA can efficiently optimize the architecture of RF to achieve better results with better computational speed. Extensive experiments are performed by utilizing the Chikungunya disease dataset. CONCLUSION: Performance analysis demonstrates that ACGA-RF achieves higher performance as compared to the competitive models in terms of F-measure, accuracy, sensitivity, and specificity. The proposed CPS system can prevent users from visiting hospitals and can render services to patients living far away from hospitals.
BACKGROUND: Artificial intelligence techniques are widely used in solving medical problems. Recently, researchers have used various deep learning techniques for the severity classification of Chikungunya disease. But these techniques suffer from overfitting and hyper-parameters tuning problems. METHODS: In this paper, an artificial intelligence-based cyber-physical system (CPS) is proposed for the severity classification of Chikungunya disease. In CPS system, the physical components are integrated with computational algorithms to provide better results. Random forest (RF) is used to design the severity classification model for Chikungunya disease. However, RF suffers from overfitting and poor computational speed problems due to complex architectures and large amounts of connection weights. Therefore, an evolving RF model is proposed using the adaptive crossover-based genetic algorithm (ACGA). RESULTS: ACGA can efficiently optimize the architecture of RF to achieve better results with better computational speed. Extensive experiments are performed by utilizing the Chikungunya disease dataset. CONCLUSION: Performance analysis demonstrates that ACGA-RF achieves higher performance as compared to the competitive models in terms of F-measure, accuracy, sensitivity, and specificity. The proposed CPS system can prevent users from visiting hospitals and can render services to patients living far away from hospitals.
Authors: Rachel Sippy; Daniel F Farrell; Daniel A Lichtenstein; Ryan Nightingale; Megan A Harris; Joseph Toth; Paris Hantztidiamantis; Nicholas Usher; Cinthya Cueva Aponte; Julio Barzallo Aguilar; Anthony Puthumana; Christina D Lupone; Timothy Endy; Sadie J Ryan; Anna M Stewart Ibarra Journal: PLoS Negl Trop Dis Date: 2020-02-14
Authors: Vemu Lakshmi; Mamidi Neeraja; M V S Subbalaxmi; M M Parida; P K Dash; S R Santhosh; P V L Rao Journal: Clin Infect Dis Date: 2008-05-01 Impact factor: 9.079